Histogram modification based image watermarking resistant to geometric distortions

Chi Man Pun, Xiao Chen Yuan

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

A geometrically invariant digital image watermarking scheme based on histogram modification is proposed in this paper. The feature extraction method called Adaptive Harris Detector with Simulated Attacks is proposed and employed, which adjusts and ranks the response threshold value of the traditional Harris Corner Detector, and trains the input image with several simulated attacks, to extract the most reliable feature points for watermark data bits embedding and extraction. The watermark embedding regions are then found as square patches centering at the selected geometric invariant feature points. In each region, the intensity-level histogram is modified by moving some pixels to form a specific pattern according to the corresponding watermark bit. For watermark extraction, the proposed Adaptive Harris Detector with Simulated Attacks is proposed to restore the watermarked image to its original position if any geometric attack exists, and to retrieve the watermarked regions. According to the pattern of intensity-level histogram distribution in these regions, a sequence of watermark bits is then extracted. Experimental results show that the proposed scheme is robust against both the geometric attacks and common signal processing, such as rotation, scaling, cropping, JPEG compression, median filtering, low-pass Gaussian filtering and also noise pollution.

Original languageEnglish
Pages (from-to)7821-7842
Number of pages22
JournalMultimedia Tools and Applications
Volume74
Issue number18
DOIs
Publication statusPublished - 28 Sept 2015
Externally publishedYes

Keywords

  • Adaptive Harris Detector with simulated attacks
  • Feature extraction
  • Geometrically invariant
  • Histogram modification

Fingerprint

Dive into the research topics of 'Histogram modification based image watermarking resistant to geometric distortions'. Together they form a unique fingerprint.

Cite this